Reconstruction-based methods are widely explored in industrial visual anomaly detection. Such methods commonly require the model to well reconstruct the normal patterns but fail in the anomalies, and thus the anomalies can be detected by evaluating the reconstruction errors. However, in practice, it's usually difficult to control the generalization boundary of the model. The model with an overly strong generalization capability can even well reconstruct the abnormal regions, making them less distinguishable, while the model with a poor generalization capability can not reconstruct those changeable high-frequency components in the normal regions, which ultimately leads to false positives. To tackle the above issue, we propose a new reconstruction network where we reconstruct the original RGB image from its gray value edges (EdgRec). Specifically, this is achieved by an UNet-type denoising autoencoder with skip connections. The input edge and skip connections can well preserve the high-frequency information in the original image. Meanwhile, the proposed restoration task can force the network to memorize the normal low-frequency and color information. Besides, the denoising design can prevent the model from directly copying the original high-frequent components. To evaluate the anomalies, we further propose a new interpretable hand-crafted evaluation function that considers both the color and gradient differences. Our method achieves competitive results on the challenging benchmark MVTec AD (97.8\% for detection and 97.7\% for localization, AUROC). In addition, we conduct experiments on the MVTec 3D-AD dataset and show convincing results using RGB images only. Our code will be available at https://github.com/liutongkun/EdgRec.
翻译:以重建为基础的方法在工业视觉异常探测中广泛探索。 这种方法通常需要模型来完善正常模式的重建,但在异常中却失败,因此可以通过评估重建错误来检测异常。 然而,在实践中,通常很难控制模型的通用边界。 过于强大的概括化能力模型甚至能够重建异常区域,使它们不易被识别,而缺乏一般化能力的模型无法在正常区域重建那些可变高频组件,最终导致错误的正面。为了解决上述问题,我们建议建立一个新的重建网络,从灰色值边缘(EdggRec)重建原始 RGB 图像。具体地说,这是通过一个UNet型的脱钩式自动编码来完成的。输入边缘和跳过连接可以保存原始图像中的高频信息。同时,拟议的恢复任务可以迫使网络仅对正常的低频率和彩色信息进行记忆化。此外,去声化设计可以防止模型直接复制原始的 RGBD 图像(Edgrequenc) 。 使用竞争性的变压性模型,我们提议在可变变的变式 BA 格式上进行新的计算。